Header menu link for other important links
X
Overcoming data sparsity in acoustic modeling of low-resource language by borrowing data and model parameters from high-resource languages
Published in International Speech and Communication Association
2016
Volume: 08-12-September-2016
   
Pages: 3037 - 3041
Abstract
In this paper, we propose two techniques to improve the acoustic model of a low-resource language by: (i) Pooling data from closely related languages using a phoneme mapping algorithm to build acoustic models like subspace Gaussian mixture model (SGMM), phone cluster adaptive training (Phone-CAT), deep neural network (DNN) and convolutional neural network (CNN). Using the low-resource language data, we then adapt the afore mentioned models towards that language. (ii) Using models built from high-resource languages, we first borrow subspace model parameters from SGMM/Phone-CAT; or hidden layers from DNN/CNN. The language specific parameters are then estimated using the lowresource language data. The experiments were performed on four Indian languages namely Assamese, Bengali, Hindi and Tamil. Relative improvements of 10 to 30% were obtained over corresponding monolingual models in each case. Copyright © 2016 ISCA.
About the journal
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
PublisherInternational Speech and Communication Association
ISSN2308457X
Open AccessYes
Concepts (16)
  •  related image
    Conformal mapping
  •  related image
    Gaussian distribution
  •  related image
    Neural networks
  •  related image
    Speech communication
  •  related image
    Speech processing
  •  related image
    Speech recognition
  •  related image
    Telephone sets
  •  related image
    CLUSTER ADAPTIVE TRAINING
  •  related image
    Convolutional neural network
  •  related image
    Cross-lingual
  •  related image
    DATA POOLING
  •  related image
    Deep neural networks
  •  related image
    Low resource languages
  •  related image
    LOW-RESOURCE
  •  related image
    SUBSPACE GAUSSIAN MIXTURE MODELS
  •  related image
    Modeling languages